Search results for "interpretability"

showing 10 items of 32 documents

Rule Extraction From Binary Neural Networks With Convolutional Rules for Model Validation.

2020

Classification approaches that allow to extract logical rules such as decision trees are often considered to be more interpretable than neural networks. Also, logical rules are comparatively easy to verify with any possible input. This is an important part in systems that aim to ensure correct operation of a given model. However, for high-dimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. Therefore, rule-based approaches are not typically used for this kind of high-dimensional data. We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN), and w…

FOS: Computer and information sciencesComputer Science - Machine Learningstochastic local searchrule extractionComputer Science - Artificial Intelligencelogical rulesQA75.5-76.95004 InformatikMachine Learning (cs.LG)Artificial Intelligence (cs.AI)Artificial IntelligenceElectronic computers. Computer scienceconvolutional neural networksk-term DNFinterpretability004 Data processingOriginal ResearchFrontiers in artificial intelligence
researchProduct

Automatic Content Analysis of Computer-Supported Collaborative Inquiry-Based Learning Using Deep Networks and Attention Mechanisms

2020

Computer-supported collaborative inquiry-based learning (CSCIL) represents a form of active learning in which students jointly pose questions and investigate them in technology-enhanced settings. Scaffolds can enhance CSCIL processes so that students can complete more challenging problems than they could without scaffolds. Scaffolding CSCIL, however, would optimally adapt to the needs of a specific context, group, and stage of the group's learning process. In CSCIL, the stage of the learning process can be characterized by the inquiry-based learning (IBL) phase (orientation, conceptualization, investigation, conclusion, and discussion). In this presentation, we illustrate the potential of a…

Feature engineeringWord embeddingComputer scienceProcess (engineering)Context (language use)neuroverkot010501 environmental sciencesoppimisanalytiikkaMachine learningcomputer.software_genre01 natural sciencesluonnollinen kielitietokoneavusteinen oppimineninquiry based learningnatural language processingyhteisöllinen oppiminentutkiva oppiminen0105 earth and related environmental sciencesInterpretabilityArtificial neural networkbusiness.industry05 social sciences050301 educationsisällönanalyysideep neural networksActive learningInquiry-based learningArtificial intelligencebusiness0503 educationcomputer
researchProduct

Assessment of the interpretability of data mining for the spatial modelling of water erosion using game theory

2021

Abstract This study undertook a comprehensive application of 15 data mining (DM) models, most of which have, thus far, not been commonly used in environmental sciences, to predict land susceptibility to water erosion hazard in the Kahorestan catchment, southern Iran. The DM models were BGLM, BGAM, Cforest, CITree, GAMS, LRSS, NCPQR, PLS, PLSGLM, QR, RLM, SGB, SVM, BCART and BTR. We identified 18 factors usually considered as key controls for water erosion, comprising 10 factors extracted from a digital elevation model (DEM), three indices extracted from Landsat 8 images, a sediment connectivity index (SCI) and three other intrinsic factors. Three indicators consisting of MAE, MBE, RMSE, and…

Hazard (logic)Hazard map010504 meteorology & atmospheric sciencesMean squared error04 agricultural and veterinary sciencesCatchment managementcomputer.software_genre01 natural sciencesShapley additive explanationsSupport vector machineErosionTopological index040103 agronomy & agricultureFeature (machine learning)Permutation feature importance measure0401 agriculture forestry and fisheriesSpatial mappingData miningDigital elevation modelGame theorycomputer0105 earth and related environmental sciencesEarth-Surface ProcessesMathematicsInterpretability
researchProduct

Frailty Status Typologies in Spanish Older Population: Associations with Successful Aging

2020

Background: Defining frailty typologies would contribute to guiding specific care interventions. These typologies could additionally be related to different health outcomes. This study aims at identifying subgroups of frail older adults based on the physical frailty phenotype and examining the relationships of these frailty profiles with quality of life and perceived health. Methods: This study relies on data from the SHARE project, namely a representative sample of 1765 Spanish-dwelling older adults identified as frail or pre-frail. Analysis included general descriptive statistics, exploratory latent class analysis (LCA) to determine the number of frailty subgroups, and LCA with covariates…

MaleGerontologyAgingFrail ElderlyHealth Toxicology and MutagenesisPopulationPsychological interventionlcsh:Medicineperceived healthArticlePerceived healthOlder populationHealthy Aging03 medical and health sciences0302 clinical medicineQuality of life (healthcare)latent class analysisHumans030212 general & internal medicine10. No inequalityGeriatric Assessmentolder adultsAgedInterpretabilityFrailtyDescriptive statisticsSuccessful aginglcsh:RPublic Health Environmental and Occupational HealthLatent class modelCross-Sectional Studiesquality of lifeFemaleIndependent Livingfrailty profilesPsychology030217 neurology & neurosurgeryInternational Journal of Environmental Research and Public Health
researchProduct

Minimum information about a biofilm experiment (MIABiE): standards for reporting experiments and data on sessile microbial communities living at inte…

2014

The minimum information about a biofilm experiment (MIABiE) initiative has arisen from the need to find an adequate and scientifically sound way to control the quality of the documentation accompanying the public deposition of biofilm-related data, particularly those obtained using high-throughput devices and techniques. Thereby, the MIABiE consortium has initiated the identification and organization of a set of modules containing the minimum information that needs to be reported to guarantee the interpretability and independent verification of experimental results and their integration with knowledge coming from other fields. MIABiE does not intend to propose specific standards on how biof…

Microbiology (medical)Databases FactualStandardizationComputer sciencemedia_common.quotation_subjectControl (management)Microbial communitiesGuidelines as TopicDocumentationBioinformaticsArticleBasic medicine03 medical and health sciencesDocumentationData standardizationTerminology as Topic:Basic medicine [Medical and Health sciences]HumansImmunology and AllergyQuality (business)Data interchangeSet (psychology)030304 developmental biologyInterpretabilitymedia_common0303 health sciencesScience & TechnologyGeneral Immunology and Microbiology030306 microbiologyBiofilmResearchMachine-readable formatsComputational Biology:Medicina básica [Ciências médicas e da saúde]General MedicineData scienceMetadataIdentification (information)Infectious DiseasesVocabulary ControlledResearch DesignMedicina básicaBiofilmsSoftwarePathogens and Disease
researchProduct

Novel 3D bio-macromolecular bilinear descriptors for protein science: Predicting protein structural classes

2015

In the present study, we introduce novel 3D protein descriptors based on the bilinear algebraic form in the ℝn space on the coulombic matrix. For the calculation of these descriptors, macromolecular vectors belonging to ℝn space, whose components represent certain amino acid side-chain properties, were used as weighting schemes. Generalization approaches for the calculation of inter-amino acidic residue spatial distances based on Minkowski metrics are proposed. The simple- and double-stochastic schemes were defined as approaches to normalize the coulombic matrix. The local-fragment indices for both amino acid-types and amino acid-groups are presented in order to permit characterizing fragme…

Models MolecularProtein structural classesMathematical parametersProtein functionQuantitative Structure-Activity RelationshipBilinear interpolationQuantitative structure activity relation3D protein descriptorBilinear formProceduresChemical structureStatistical parametersMinkowski spaceProtein analysisAmino AcidsPriority journalMathematicsInterpretabilityQuantitative Biology::BiomoleculesApplied MathematicsStatistical parameterValidation studyGeneral MedicineComputer simulationDiscriminant analysisReproducibilityAmino acidAlgorithmChemistryProtein conformationModeling and SimulationStatistical modelGeneral Agricultural and Biological SciencesBiological systemAmino acid analysisAlgorithmsNonbiological modelStatistics and ProbabilityCorrelation coefficientLDAMacromolecular SubstancesMarkov chainMacromoleculeStructure analysisModels BiologicalArticleGeneral Biochemistry Genetics and Molecular BiologyCombinatoricsStochastic processesBilinear formBiologyMatrixGeneral Immunology and MicrobiologyProteinCoulombic matrixComputational BiologyProteinsReproducibility of ResultsLinear discriminant analysisWeightingCorrelation coefficientProtein structureBiological modelLinear ModelsThree-dimensional modelingJournal of Theoretical Biology
researchProduct

Closed-Form Expressions for Global and Local Interpretation of Tsetlin Machines

2021

Tsetlin Machines (TMs) capture patterns using conjunctive clauses in propositional logic, thus facilitating interpretation. However, recent TM-based approaches mainly rely on inspecting the full range of clauses individually. Such inspection does not necessarily scale to complex prediction problems that require a large number of clauses. In this paper, we propose closed-form expressions for understanding why a TM model makes a specific prediction (local interpretability). Additionally, the expressions capture the most important features of the model overall (global interpretability). We further introduce expressions for measuring the importance of feature value ranges for continuous feature…

Range (mathematics)Interpretation (logic)Theoretical computer scienceScale (ratio)Process (engineering)Computer scienceFeature (machine learning)Value (computer science)Propositional calculusInterpretability
researchProduct

Mutual nonlinear prediction as a tool to evaluate coupling strength and directionality in bivariate time series: Comparison among different strategie…

2008

We compare the different existing strategies of mutual nonlinear prediction regarding their ability to assess the coupling strength and directionality of the interactions in bivariate time series. Under the common framework of $k$-nearest neighbor local linear prediction, we test three approaches based on cross prediction, mixed prediction, and predictability improvement. The measures of interdependence provided by these approaches are first evaluated on short realizations of bivariate time series generated by coupled Henon models, investigating also the effects of noise. The usefulness of the three mutual nonlinear prediction schemes is then assessed in a common physiological application d…

Series (mathematics)Computer scienceBivariate analysisCondensed Matter PhysicSynchronizationk-nearest neighbors algorithmNoisePhysics and Astronomy (all)StatisticsSettore ING-INF/06 - Bioingegneria Elettronica E InformaticaPredictabilityTime seriesAlgorithmMathematical PhysicsInterpretabilityStatistical and Nonlinear Physic
researchProduct

Classification of diabetes-related retinal diseases using a deep learning approach in optical coherence tomography

2019

Background and objectives: Spectral Domain Optical Coherence Tomography (SD-OCT) is a volumetric imaging technique that allows measuring patterns between layers such as small amounts of fluid. Since 2012, automatic medical image analysis performance has steadily increased through the use of deep learning models that automatically learn relevant features for specific tasks, instead of designing visual features manually. Nevertheless, providing insights and interpretation of the predictions made by the model is still a challenge. This paper describes a deep learning model able to detect medically interpretable information in relevant images from a volume to classify diabetes-related retinal d…

Volumetric imagingComputer scienceProfundo InterpretabilidadConvolutional neural network030218 nuclear medicine & medical imagingPattern Recognition Automatedchemistry.chemical_compoundMacular Degeneration[SPI]Engineering Sciences [physics]0302 clinical medicineDeep learning modelsInterpretabilityModelos de aprendizajeAged 80 and overArtificial neural networkmedicine.diagnostic_testMedical findings KeyWords Plus:MACULAR DEGENERATIONAngiographyMiddle AgedRetinal diseases3. Good healthComputer Science ApplicationsArea Under CurveTomographyMedical findingsAlgorithmsTomography Optical CoherenceAprendizaje - ModelosDiabetic macular edemaHealth InformaticsHallazgos médicosMacular Edema03 medical and health sciencesDeep LearningOptical coherence tomographymedicine[INFO.INFO-IM]Computer Science [cs]/Medical ImagingDeep InterpretabilityHumans[INFO]Computer Science [cs]Enfermedades de la retinaRetinopathyAgedDiabetic RetinopathyOptical coherence tomographybusiness.industryDeep learningReproducibility of ResultsRetinalPattern recognitionMacular degenerationmedicine.diseasechemistryArtificial intelligenceNeural Networks ComputerLa tomografía de coherencia ópticabusinessClassifier (UML)030217 neurology & neurosurgerySoftware
researchProduct

Metric Learning in Histopathological Image Classification: Opening the Black Box

2023

The application of machine learning techniques to histopathology images enables advances in the field, providing valuable tools that can speed up and facilitate the diagnosis process. The classification of these images is a relevant aid for physicians who have to process a large number of images in long and repetitive tasks. This work proposes the adoption of metric learning that, beyond the task of classifying images, can provide additional information able to support the decision of the classification system. In particular, triplet networks have been employed to create a representation in the embedding space that gathers together images of the same class while tending to separate images w…

WSItriplet networksembeddingSettore INF/01 - Informaticapatient level accuracymetric learningbreast cancer imagingBreakHisclassification interpretabilityvisualization
researchProduct